EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning

EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning Ashish Seth author Ramaneswaran Selvakumar author S Sakshi author Sonal Kumar author Sreyan Ghosh author Dinesh Manocha author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication seth-etal-2024-eh 10.18653/v1/2024.emnlp-main.366 https://aclanthology.org/2024.emnlp-main.366/ 2024-11 6386 6400